Spaces:
Running
Running
File size: 1,437 Bytes
1ea4a0e f39e5b2 1ea4a0e c950bff 4419042 f39e5b2 4419042 f39e5b2 1ea4a0e f39e5b2 1ea4a0e f39e5b2 1ea4a0e 791b415 46b69e2 1ea4a0e 791b415 1ea4a0e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
import gradio as gr
from huggingface_hub import InferenceClient
import os
hf_token = os.getenv("HF_TOKEN").strip()
api_key = os.getenv("HF_KEY").strip()
model_name = os.getenv("Z3TAAGI_ACC).strip()
system_prompt = os.getenv("SYSTEM_PROMPT").strip()
client = InferenceClient(model_name)
def respond(
message,
history: list[tuple[str, str]],
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_prompt}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
# Gradio UI
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Maximum Response Length"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Creativity"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Neural Activity")
],
theme="glass",
)
if __name__ == "__main__":
demo.launch()
|